Patent PreCheck

by Patent-PreCheck · remote · local (npm) · no sign-in to list tools · v0.4.1 · published by GitHub user Patent-PreCheck

Keyless 12-tool patentability MCP: USPTO pillar scores, prior art, hosted at patentprecheck.com/mcp.

Changes · 8

Compare Registry entry

12 tools: 8 change things and 4 only read.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone0Claude Code: ask
Changes things8Claude Code: ask: see these tools
Only reads4Claude Code: allow: see these tools

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http patent-precheck https://patentprecheck.com/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

12 tools

Changes things 8Creates or changes something that can be changed back.Claude Code: ask

precheck_compare_to_patentCompare invention text to a known US patent: embedding similarity plus prior-art risk analysis (statute hints, overlap theme, distinction checklist).No findings
Why it is in this group
- The name "precheck_compare_to_patent" says "compare": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
Description, as the server wrote it
Compare invention text to a known US patent: embedding similarity plus prior-art risk analysis (statute hints, overlap theme, distinction checklist). Use when the user names a specific reference patent.
precheck_cpc_suggestSuggest Cooperative Patent Classification (CPC) codes for an invention description.No findings
Why it is in this group
- The input takes a statement or command to run (input.code), which can change anything it can reach.
Description, as the server wrote it
Suggest Cooperative Patent Classification (CPC) codes for an invention description. Offline heuristic — informational only. No network call.
precheck_legal_contextReturn a short snippet of current US software-patent legal guidance (CAFC, USPTO, Alice/§101) relevant to scoring this invention.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
Description, as the server wrote it
Return a short snippet of current US software-patent legal guidance (CAFC, USPTO, Alice/§101) relevant to scoring this invention. Informational only — not legal advice.
precheck_prior_artReturn the closest prior-art matches consulted for an invention (titles, sources, similarity scores, URLs).No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
Description, as the server wrote it
Return the closest prior-art matches consulted for an invention (titles, sources, similarity scores, URLs). Runs the same analyze pipeline as precheck_score but focuses on retrieval results. Pass invention text via `code`.
precheck_rejection_patternsPreview examination-risk signals: similar office-action rejections, abandonment patterns, and the primary statutory basis an examiner might cite (§101/§102/§103).No findings
Why it is in this group
- The description's first verb is "preview": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
Description, as the server wrote it
Preview examination-risk signals: similar office-action rejections, abandonment patterns, and the primary statutory basis an examiner might cite (§101/§102/§103). Use after precheck_score to explain prosecution risk.
precheck_scoreRun a prior-art density / risk-profile pre-check on source code or an invention description.No findings
Why it is in this group
- The description's first verb is "run": a word for a change.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
Description, as the server wrote it
Run a prior-art density / risk-profile pre-check on source code or an invention description. Returns a 0–100 directional score across the four USPTO statutory pillars (§101 eligibility, §102 novelty, §103 non-obviousness, §101 utility), a separate §112 filing-readiness signal, the band (Not Ready → File Ready), the pillar that holds the band back, opportunities to thicken the technical description, and a count of prior-art matches consulted. Show filename + size and get user yes, then pass confirm_upload: true. Pass the text inline via `code`.
precheck_search_corpusFast semantic search against the 2,200,000+ prior-art corpus without LLM scoring.No findings
Why it is in this group
- The name "precheck_search_corpus" says "search": a word for reading.
- The input takes a statement or command to run (input.code), which can change anything it can reach.
Description, as the server wrote it
Fast semantic search against the 2,200,000+ prior-art corpus without LLM scoring. Returns ranked matches with similarity scores. Cheaper than precheck_score when you only need references.
precheck_start_reviewReturn the URL where the user can start a paid (or promo-unlocked) Interactive Code Review that strengthens each pillar with evidence and produces a filing package.No findings
Why it is in this group
- The name "precheck_start_review" says "start": a word for a change.
Description, as the server wrote it
Return the URL where the user can start a paid (or promo-unlocked) Interactive Code Review that strengthens each pillar with evidence and produces a filing package. Use after precheck_score when the user wants to act on the result.

Only reads 4Looks things up and changes nothing.Claude Code: allow

precheck_deliverablesReturn download URLs for finalized ICR deliverables (filing packet, coaching report, package zip, scorecard PDF).No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it
Return download URLs for finalized ICR deliverables (filing packet, coaching report, package zip, scorecard PDF). Requires report_id and session_key.
precheck_lookup_patentResolve a US patent or application number (e.g.No findings
Why it is in this group
- The name "precheck_lookup_patent" says "lookup": a word for reading.
Description, as the server wrote it
Resolve a US patent or application number (e.g. US1234567B2) via USPTO Open Data Portal and optionally join the indexed prior-art corpus. Returns title, status, CPC, grant-text excerpt, and a public URL. No API key required in the MCP client.
precheck_pillarsList the five scoring pillars (with statutes and weights) and the band rules used by precheck_score.No findings
Why it is in this group
- The description's first verb is "list": a word for reading.
Description, as the server wrote it
List the five scoring pillars (with statutes and weights) and the band rules used by precheck_score. Use this to explain a score to the user. No network call.
precheck_session_statusReturn status for an active Interactive Code Review session.Reads text others writeNo findings
Why it is in this group
- The name "precheck_session_status" says "status": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "return" and "review": it reads comments, which other people can write.
Description, as the server wrote it
Return status for an active Interactive Code Review session. Requires report_id and session_key from the user access email link.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0: Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write1: Brings in text someone else can write: web pages, inbound email, messages, issues and comments.; precheck_session_status
Can send data out0: Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Looked at Oct 22, 2026, 14:54 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable: yes
HTTP status of an anonymous initialize: 200
tools/list served without credentials: yes
Tools that change things, listed without credentials: 8
Protocol version: 2025-06-18
WWW-Authenticate on 401: not observed
resource_metadata in WWW-Authenticate: none
RFC 9728 protected resource metadata: none
Authorization servers: none
Legacy HTTP+SSE transport: no
Dynamic client registration: not observed
Client ID metadata documents: not observed

WarnThe whole server
The endpoint served tools/list without credentials, and the list has 8 tools that change things (8 write). Whether a call also works without credentials was not tested: tools are never called.
Matched text
https://patentprecheck.com/mcp: tools/list returned 12 tools to an anonymous client, including precheck_score (write), precheck_prior_art (write), precheck_rejection_patterns (write), precheck_legal_context (write), precheck_start_review (write) and 3 more
What this check looks for

Install

Pinned to version 0.4.1. Values in angle brackets are yours to fill in.

claude mcp add --transport http patent-precheck https://patentprecheck.com/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__patent-precheck__precheck_pillars",
      "mcp__patent-precheck__precheck_session_status",
      "mcp__patent-precheck__precheck_deliverables",
      "mcp__patent-precheck__precheck_lookup_patent"
    ],
    "ask": [
      "mcp__patent-precheck__precheck_score",
      "mcp__patent-precheck__precheck_prior_art",
      "mcp__patent-precheck__precheck_rejection_patterns",
      "mcp__patent-precheck__precheck_legal_context",
      "mcp__patent-precheck__precheck_start_review",
      "mcp__patent-precheck__precheck_search_corpus",
      "mcp__patent-precheck__precheck_cpc_suggest",
      "mcp__patent-precheck__precheck_compare_to_patent"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as patent-precheck. Review it before you use it.

Capability tags behind 1 rule

mcp__patent-precheck__precheck_session_status untrusted-input

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.Patent-PreCheck/patent-precheck/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

8 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry. Synced Oct 21, 2026, 18:18 UTC.

For agents: Markdown · JSON · report this listing